© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89777
    Prev
    Next
    INDEX
    Explanations

    choice or option

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on numeric tokens (e.g. standalone numbers, years, amounts, or other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actions
    -0.83
    arpur
    -0.82
    mær
    -0.78
    reonine
    -0.76
     første
    -0.76
     "{\"
    -0.75
     scenarios
    -0.75
    män
    -0.75
     我
    -0.74
    人を
    -0.73
    POSITIVE LOGITS
     your
    1.64
     charity
    1.14
    YOUR
    0.99
     donor
    0.97
     of
    0.91
     kanilang
    0.88
     osob
    0.87
     branca
    0.87
     own
    0.85
    curité
    0.83
    Activations Density 0.020%

    No Known Activations